!pip install wordcloud

import pandas as pd import matplotlib.pyplot as plt %matplotlib inline import seaborn as sns from wordcloud import WordCloud from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.metrics.pairwise import linear_kernel sns.set_style('darkgrid')

## reading dataset df_movies = pd.read_csv(r'C:\Users\jgaur\Downloads\Gaurav 50\Data Science Project 4 - Movie Recommendation System\movies.csv') df_rating = pd.read_csv(r'C:\Users\jgaur\Downloads\Gaurav 50\Data Science Project 4 - Movie Recommendation System\ratings.csv')

## displaying first 5 rows of movies dataset df_movies.head()

## displaying last 5 rows of ratings dataset df_rating.tail()

print("Movies data shape: ", df_movies.shape) print("Ratings data shape: ", df_rating.shape)

## checking null values in movies dataset df_movies.isnull().sum()

## checking null values in ratings dataset df_rating.isnull().sum()

df_movies.genres.unique()

total_genres = [] for g in df_movies.genres: g = g.split('|') ## spliting every generes from '|' ## checking if the is not present in the list if g not in total_genres: total_genres.append(g)

total_genres

df_movies.title.head()

df_movies.title[0][:-7]

year, title = [], [] for t in df_movies.title: title.append(t[:-7]) year.append(t[-7:])

year[:5], title[:5]

word_cloud_genre=WordCloud(width=1500,height=800,background_color='black',min_font_size=2 , min_word_length=3).generate(str(total_genres)) word_cloud_title=WordCloud(width=1500,height=800,background_color='cyan',min_font_size=2 , min_word_length=3).generate(str(title))

plt.figure(figsize=(20,10)) plt.axis('off') plt.title('Word Cloud for Movies Genre',fontsize=30) plt.imshow(word_cloud_genre);

plt.figure(figsize=(20,10)) plt.axis('off') plt.title('Word Cloud for Movies Title',fontsize=30) plt.imshow(word_cloud_title);

final_df = pd.merge(df_rating, df_movies, how='left',on='movieId')

final_df.head()

title_rating = final_df.groupby(['title'])[['rating']].sum() title_rating = title_rating.nlargest(10,'rating') title_rating.head()

plt.figure(figsize=(10, 10)) plt.xticks(rotation=75); sns.barplot(title_rating.index, title_rating['rating']); plt.ylabel('Title'); plt.xlabel('Count');

tfidf = TfidfVectorizer() tfidf_matrix = tfidf.fit_transform(df_movies['genres'])

movie_user = final_df.pivot_table(index='userId',columns='title',values='rating') movie_user.head()

cos_similarity = linear_kernel(tfidf_matrix, tfidf_matrix)

indices=pd.Series(df_movies.index,index=df_movies['title']) titles=df_movies['title'] def recom_sys(title): idx = indices[title] similarity_scores = list(enumerate(cos_similarity[idx])) similarity_scores = sorted(similarity_scores, key=lambda x: x[1], reverse=True) similarity_scores = similarity_scores[1:21] movie_indices = [i[0] for i in similarity_scores] return titles.iloc[movie_indices]

recom_sys('Grumpier Old Men (1995)')

titles